Skip to content

[core] do not send error across process #16174

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 8, 2025
Merged

[core] do not send error across process #16174

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions vllm/v1/executor/multiproc_executor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,10 +119,9 @@ def collective_rpc(self,
timeout=dequeue_timeout)

if status != WorkerProc.ResponseStatus.SUCCESS:
if isinstance(result, Exception):
raise result
else:
raise RuntimeError("Worker failed")
raise RuntimeError(
"Worker failed with error %s, please check the"
" stack trace above for the root cause", result)

responses[w.rank] = result

Expand Down Expand Up @@ -378,9 +377,11 @@ def worker_busy_loop(self):
# Notes have been introduced in python 3.11
if hasattr(e, "add_note"):
e.add_note(traceback.format_exc())
self.worker_response_mq.enqueue(
(WorkerProc.ResponseStatus.FAILURE, e))
logger.exception("WorkerProc hit an exception: %s", exc_info=e)
# exception might not be serializable, so we convert it to
# string, only for logging purpose.
self.worker_response_mq.enqueue(
(WorkerProc.ResponseStatus.FAILURE, str(e)))
continue

self.worker_response_mq.enqueue(
Expand Down